Diffus
Loslegen
modelle/Chroma - v.35-detail-calibrated

Chroma - v.35-detail-calibrated

Lodestone
|
6/30/2025
|
1:24:59 PM
| Discussion|
0
A hyper-realistic painting of a grotesque alien creature with a translucent dome-like head, rough textured reddish skin, a curved beak-like mouth, muscular upper body, and dark bead-like protrusions on shoulders.
Anime style scene of a solitary figure standing on a mountain cliff overlooking a vast expanse of green landscape under a moody, detailed sky filled with sunset clouds.
A glowing round ball with large anime-style eyes and an open mouth sits on a fiery, molten surface under dramatic lighting.
Dark mysterious cat with glowing orange eyes holding a beer bottle in a cinematic and detailed composition.
A fierce feral cat with wide eyes aggressively wielding a chainsaw, rampaging through a bustling fish market under a bright blue sky.
Digital painting of a glowing skeletal dragon head with icy blue hues, hollow eyes, and rough texture against a dark abstract background.
Group of cute kodama spirits posing in a magical forest with dark ominous figures in the background, depicted in a cinematic low angle style.
A vibrant digital painting of a moss-covered cottage with a thatched roof and wooden door, surrounded by lush greenery and bright orange autumn foliage under clear blue skies.
A moody, cinematic silhouette of a baseball player striking a ball with a bat, showing an explosive impact effect amid a cloudy sky and stadium lights.
A grotesque skeletal creature with multiple skulls fused on its head and shoulders, glowing yellow eyes, decayed and cracked skin with red and brown hues, set against a muted background with high contrast dramatic lighting.
A massive mechanical steampunk-style structure hovering above a foggy landscape with power lines and a dirt path below.
Detailed atmospheric sketch of an old woman with a deeply wrinkled face, wearing a dark hood, expressing loneliness and cold emotions.

Empfohlene Prompts

Extreme close-up photograph of a single tiger eye, direct frontal view. The iris is very detailed and the pupil resembling a dark void. The word "Chroma V.35 now with less steps" is across the lower portion of the image in large white stylized letters, with brush strokes resembling those made with Japanese calligraphy. Each strand of the thick fur is highly detailed and distinguishable. Natural lighting to capture authentic eye shine and depth.

Empfohlene Negative Prompts

low quality, ugly, unfinished, out of focus

Empfohlene Parameter

samplers

Euler

steps

16

cfg

4.5

Tipps

Chroma offers alternative quantization options including FP8 Scaled Quant (useful for inference speed with ComfyUI) and GGUF Quantized format (requires ComfyUI-GGUF custom node).

The model is still training, so community feedback is highly encouraged.

Support for ongoing training of open-source AI models can be done via Ko-fi or Ethereum donations.

Ersteller-Sponsoren

Fictional.ai support

Shoutout to Fictional.ai for the awesome support — seriously appreciate you helping push open-source AI forward.

Hey everyone!

Chroma is a 8.9B parameter model based on FLUX.1-schnell (technical report coming soon!). It’s fully Apache 2.0 licensed, ensuring that anyone can use, modify, and build on top of it—no corporate gatekeeping.

The model is still training right now, and I’d love to hear your thoughts! Your input and feedback are really appreciated.

What Chroma Aims to Do

  • Training on a 5M dataset, curated from 20M samples including anime, furry, artistic stuff, and photos.

  • Fully uncensored, reintroducing missing anatomical concepts.

  • Built as a reliable open-source option for those who need it.

See the Progress

Quantization options

Special Thanks

Shoutout to Fictional.ai for the awesome support — seriously appreciate you helping push open-source AI forward.

Support Open-Source AI

The current pretraining run has already used 5000+ H100 hours, and keeping this going long-term is expensive.

If you believe in accessible, community-driven AI, any support would be greatly appreciated.

👉 [https://ko-fi.com/lodestonerock/goal?g=1] — Every bit helps!

ETH: 0x679C0C419E949d8f3515a255cE675A1c4D92A3d7

my discord: discord.gg/SQVcWVbqKx

Zurück
Realistic Vision V6.0 B1 - V5.1 (VAE)
Weiter
Stable Diffusion 3.5 Large - Large
Dieses Modell verwenden

Modell-Details

Modelltyp

Checkpoint

Basismodell

Other

Modellversion

v.35-detail-calibrated

Modell-Hash

e01d54637f

Ersteller

Lodestone's avatar
Lodestone

Diskussion

Bitte log in um einen Kommentar zu hinterlassen.

Bilder von Chroma - v.35-detail-calibrated

Bilder mit basismodell

Bilder mit chroma